© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 95027
    Prev
    Next
    INDEX
    Explanations

    working, production, Trader

    np_acts-logits-general · gemini-2.5-flash-lite

    handle affairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     సీ
    0.49
    وسي
    0.48
    gcf
    0.46
    eyse
    0.46
    ím
    0.45
    ш
    0.45
    ى
    0.44
    \},\
    0.43
    ์
    0.43
     пяти
    0.43
    POSITIVE LOGITS
     lavor
    0.53
     lavorare
    0.48
     commentary
    0.45
     Verdana
    0.44
     anabolic
    0.44
     defra
    0.44
     working
    0.44
     Trabal
    0.43
    AQ
    0.43
    لې
    0.43
    Activations Density 0.001%

    No Known Activations